INDEX

Explanations

physical actions or interactions between characters, especially related to eyes and physical contact

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

senal

-0.70

 Flavoring

-0.68

ivals

-0.67

 Families

-0.66

soDeliveryDate

-0.64

ships

-0.64

enario

-0.63

 Franch

-0.63

 ourselves

-0.60

uesday

-0.59

POSITIVE LOGITS

 numb

0.93

stretched

0.84

 throb

0.81

 clenched

0.79

 swollen

0.77

 hers

0.76

 protr

0.76

 amput

0.73

 gripped

0.69

 blurry

0.69

Activations Density 13.800%

physical actions or interactions between characters, especially related to eyes and physical contact

No Comments

No Known Activations